Look. Decision-making is difficult, and decisions have to be made constantly.
What should I be for Halloween? Do I need a Porsche? Should I dump that loser? Is Phoenix a good place to retire? Whom should I vote for? What toe ring should I buy?

It’s a cruel world out there. Coin-flipping, I Ching consultation, closing your eyes and jumping, postponing the inevitable, Rock-Paper-Scissors, and asking your sister are all time-honored means of coming to a decision — and yet we think there’s room for one more: Hunch.

In 10 questions or less, Hunch will offer you a great solution to your problem, concern or dilemma, on hundreds of topics. Hunch’s answers are based on the collective knowledge of the entire Hunch community, narrowed down to people like you, or just enough like you that you might be mistaken for each other in a dark room. Hunch is designed so that every time it’s used, it learns something new. That means Hunch’s hunches are always getting better.

Hunch was started by clever folks who were exploring how machine learning could be used to guide practical decision-making.

We think that you will love Hunch. It may not be awesome yet — a lot of people have to contribute to it before it knows much of anything. But it will be awesome later. Love it anyway. Love it now.

For a normal person’s overview of what Hunch is, see our about page. But if, like many of us, you’re the type of person who likes to watch those “how it works” shows, here’s a little more detail that might appeal to your inner geek.

Researchers have documented how decisions made by diverse and independent groups of people are often superior to those made by individuals – even experts. The reason is that knowledge is often spread among many people. The challenge is to identify it, collect it, and effectively use it.

Take, for example, expertise about colleges or cars. In a random, large group of people, most probably know something about a few examples (say, the college someone attended or the car they currently drive) but are not experts on the topic as a whole (as a college guidance counselor or auto executive might be). If you were able to collect and organize all the various bits of individual knowledge that the large group possesses, you’d have a pretty complete picture of the topic overall.

At the core of Hunch is a question selection algorithm built by our small gaggle of MIT computer scientists with backgrounds in machine learning. The algorithm is always asking itself, “What can I ask you next which will lead to the best possible result for this decision?” The choice of which questions to ask and when to ask them will vary based on what you’ve already been asked (and how you’ve answered) so far, the same way that a human expert would adjust a line of questioning based on your responses. The idea is that if someone says they’re a vegetarian, you don’t want to then immediately ask them how they want their steak cooked.

In choosing what to ask you, Hunch’s question selection algorithm tries to do two things. First, it tries to find a question which will discriminate well among the remaining possible decision outcomes for you – thus filtering the remaining choices from “many” to “fewer”. Second, the algorithm looks for a question which can help optimize and rank the remaining decision results to present you with the ones you’ll like the most. It’s trying to ensure that you’ll like outcome #1 better than outcome #5.

As you answer questions, Hunch can narrow down your possible decision outcomes because each outcome can be “trained” to correspond with each question’s answers. Any logged in user can set initial training or correct existing training, in addition to proposing new topics, questions to ask, and decision outcomes. This is how Hunch is truly a collection of common knowledge. So whether you happen to know a great question that would lead someone to a Sancerre vs. a Pinot Grigio, or you’d like to clarify that “Whatever Happened to Baby Jane” is probably more of a “campy” than a “cult” movie, Hunch absorbs your input and uses it to provide smarter decision results for the next user.

Besides users explicitly training and contributing to Hunch, there’s a second way that Hunch learns, especially for what we call ‘Teach Hunch About You’ questions which have more to do with you as a person than with your preferences for a specific topic’s objective decision criteria. When a user clicks “Yes” or “No” to indicate whether or not they like a decision result, Hunch incrementally strengthens or weakens the mathematical correlation between that result and any ‘Teach Hunch About You’ questions that have been answered so far. So over time, Hunch might learn that people living in cities tend to prefer diet sodas, or that SCUBA divers tend to like bicycles with lots of gears. (we just made those examples ups, but you get the idea.) The academic name for this sort of algorithm is machine learning.

So, like we said…
Hunch is designed to soak up collective knowledge and then organize it in a useful way to help you make smart decisions. Hunch proposes custom decision results for you that it wouldn’t necessarily give to somebody else. But at its core, Hunch’s decision making algorithm is just a mathematical framework. It’s the users of Hunch who give the algorithm proper training and personality by contributing to it and making it clever, funny, and nuanced…. but most of all very useful in helping everyone to make smart, efficient decisions.

Source: Hunch.com

This entry was posted on Monday, June 15th, 2009 at 9:57 am and is filed under Innovations, Newcomers. You can follow any responses to this entry through the RSS 2.0 feed. You can leave a response, or trackback from your own site.